Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to "cards" or related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mostra
    -0.43
    "))
    -0.41
     Stephenson
    -0.40
     {}));
    -0.40
     }}}
    -0.39
     divisão
    -0.39
    }}\
    -0.39
     EconPapers
    -0.39
     the
    -0.38
     habr
    -0.38
    POSITIVE LOGITS
     Cards
    1.30
     card
    1.30
     Card
    1.27
    Cards
    1.25
    Card
    1.24
     cards
    1.22
     CARDS
    1.20
     CARD
    1.14
    CARD
    1.09
    card
    1.04
    Act Density 0.095%

    No Known Activations